Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4449 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.8327. Min Range: -15.8327
Max Act: 15.8327. Min Act: -0.1700
Data Index: 3923109 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.8327. Min Range: -15.8327
Max Act: 15.8327. Min Act: -0.1700
Data Index: 8129654 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.8327. Min Range: -15.8327
Max Act: 15.7702. Min Act: -0.1700
Data Index: 1494776 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.8327. Min Range: -15.8327
Max Act: 15.7077. Min Act: -0.1700
Data Index: 5593493 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.8327. Min Range: -15.8327
Max Act: 15.7077. Min Act: -0.1700
Data Index: 4418440 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.8327. Min Range: -15.8327
Max Act: 15.5827. Min Act: -0.1700
Data Index: 7836724 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.8327. Min Range: -15.8327
Max Act: 15.5827. Min Act: -0.1700
Data Index: 1106143 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.8327. Min Range: -15.8327
Max Act: 15.5827. Min Act: -0.1700
Data Index: 6855662 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.8327. Min Range: -15.8327
Max Act: 15.5202. Min Act: -0.1700
Data Index: 8296842 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.8327. Min Range: -15.8327
Max Act: 15.5202. Min Act: -0.1700
Data Index: 4269444 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.8327. Min Range: -15.8327
Max Act: 15.5202. Min Act: -0.1700
Data Index: 2368989 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.8327. Min Range: -15.8327
Max Act: 15.3952. Min Act: -0.1700
Data Index: 2098578 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.8327. Min Range: -15.8327
Max Act: 15.4577. Min Act: -0.1700
Data Index: 3549570 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.8327. Min Range: -15.8327
Max Act: 15.4577. Min Act: -0.1700
Data Index: 1558642 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.8327. Min Range: -15.8327
Max Act: 15.4577. Min Act: -0.1700
Data Index: 7203514 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.8327. Min Range: -15.8327
Max Act: 15.4577. Min Act: -0.1700
Data Index: 5213452 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.8327. Min Range: -15.8327
Max Act: 15.3952. Min Act: -0.1700
Data Index: 3613073 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.8327. Min Range: -15.8327
Max Act: 15.3327. Min Act: -0.1700
Data Index: 1238839 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.8327. Min Range: -15.8327
Max Act: 15.3327. Min Act: -0.1700
Data Index: 1761786 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.8327. Min Range: -15.8327
Max Act: 15.3327. Min Act: -0.1700
Data Index: 5192306 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19